<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koehn-senellart-2010-convergence">
    <titleInfo>
        <title>Convergence of Translation Memory and Statistical Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Koehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean</namePart>
        <namePart type="family">Senellart</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2010-nov 4</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Joint EM+/CNGL Workshop: Bringing MT to the User: Research on Integrating MT in the Translation Industry</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ventsislav</namePart>
            <namePart type="family">Zhechev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">Denver, Colorado, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present two methods that merge ideas from statistical machine translation (SMT) and translation memories (TM). We use a TM to retrieve matches for source segments, and replace the mismatched parts with instructions to an SMT system to fill in the gap. We show that for fuzzy matches of over 70%, one method outperforms both SMT and TM baselines.</abstract>
    <identifier type="citekey">koehn-senellart-2010-convergence</identifier>
    <location>
        <url>https://aclanthology.org/2010.jec-1.4</url>
    </location>
    <part>
        <date>2010-nov 4</date>
        <extent unit="page">
            <start>21</start>
            <end>32</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Convergence of Translation Memory and Statistical Machine Translation
%A Koehn, Philipp
%A Senellart, Jean
%Y Zhechev, Ventsislav
%S Proceedings of the Second Joint EM+/CNGL Workshop: Bringing MT to the User: Research on Integrating MT in the Translation Industry
%D 2010
%8 nov 4
%I Association for Machine Translation in the Americas
%C Denver, Colorado, USA
%F koehn-senellart-2010-convergence
%X We present two methods that merge ideas from statistical machine translation (SMT) and translation memories (TM). We use a TM to retrieve matches for source segments, and replace the mismatched parts with instructions to an SMT system to fill in the gap. We show that for fuzzy matches of over 70%, one method outperforms both SMT and TM baselines.
%U https://aclanthology.org/2010.jec-1.4
%P 21-32

Markdown (Informal)

[Convergence of Translation Memory and Statistical Machine Translation](https://aclanthology.org/2010.jec-1.4) (Koehn & Senellart, JEC 2010)

• Convergence of Translation Memory and Statistical Machine Translation (Koehn & Senellart, JEC 2010)

ACL

• Philipp Koehn and Jean Senellart. 2010. Convergence of Translation Memory and Statistical Machine Translation. In Proceedings of the Second Joint EM+/CNGL Workshop: Bringing MT to the User: Research on Integrating MT in the Translation Industry, pages 21–32, Denver, Colorado, USA. Association for Machine Translation in the Americas.